Urambazaji
AI BENCHY
Advertise here

AI BENCHY Compare

DeepSeek: DeepSeek V3.2 vs Inception: Mercury 2

Benchmark zimetengenezwa kutoka seti za majaribio za AI BENCHY tarehe: 2026-06-03

Kipimo DeepSeek V3.2 DeepSeek V3.2 none Toleo: 2025-12-01 Mercury 2 Mercury 2 none Toleo: 2026-02-24
Alama 5.4 4.6
Nafasi #130 #153
Uaminifu 10.0 10.0
Uthabiti 7.5 9.1
Majaribio sahihi
Kiwango cha kupita kwa kila jaribio 41.7% 25.0%
Majaribio yasiyo thabiti 6 2
Jumla ya uendeshaji 60 60
Gharama kwa matokeo 0.296 0.216
Jumla ya gharama $0.017 $0.009
Bei ya ingizo $0.229 / 1M $0.250 / 1M
Bei ya toleo $0.344 / 1M $0.750 / 1M
Jumla ya tokeni za ingizo 53,408 25,515
Tokeni za matokeo 11,159 3,001
Tokeni za hoja 0 0
Muda wa majibu (wastani) 14.43s 614ms
Muda wa majibu (upeo) 115.89s 1.27s
Muda wa majibu (jumla) 288.55s 12.28s

Modeli bora kwa alama

Alama dhidi ya gharama ya jumla

Muda wa majibu (wastani)

Alama vs Muda wa majibu (wastani)

Jumla ya tokeni za matokeo

Alama vs Jumla ya tokeni za matokeo

Mgawanyo wa kategoria

Mbinu za kupinga AI Alama Uthabiti Kiwango cha kupita kwa kila jaribio Majaribio yasiyo thabiti Majaribio sahihi Muda wa majibu (wastani) Tokeni za ingizo Tokeni za matokeo Tokeni za hoja
DeepSeek V3.2 3.2 8.0 8.3% 1 9.35s 494 1,073 0
Mercury 2 3.0 10.0 0.0% 0 483ms 631 286 0
Uandishi wa msimbo Alama Uthabiti Kiwango cha kupita kwa kila jaribio Majaribio yasiyo thabiti Majaribio sahihi Muda wa majibu (wastani) Tokeni za ingizo Tokeni za matokeo Tokeni za hoja
DeepSeek V3.2 3.1 5.4 16.7% 1 20.87s 4,690 4,522 0
Mercury 2 3.5 9.4 0.0% 0 831ms 4,631 1,650 0
Mchanganyiko Alama Uthabiti Kiwango cha kupita kwa kila jaribio Majaribio yasiyo thabiti Majaribio sahihi Muda wa majibu (wastani) Tokeni za ingizo Tokeni za matokeo Tokeni za hoja
DeepSeek V3.2 6.5 10.0 0.0% 0 115.89s 29,843 2,887 0
Mercury 2 3.0 10.0 0.0% 0 606ms 4,821 131 0
Uchanganuzi na uchimbaji wa data Alama Uthabiti Kiwango cha kupita kwa kila jaribio Majaribio yasiyo thabiti Majaribio sahihi Muda wa majibu (wastani) Tokeni za ingizo Tokeni za matokeo Tokeni za hoja
DeepSeek V3.2 6.3 5.8 66.7% 1 9.42s 7,890 1,710 0
Mercury 2 7.3 5.9 83.3% 1 667ms 6,362 180 0
Mahususi kwa domeni Alama Uthabiti Kiwango cha kupita kwa kila jaribio Majaribio yasiyo thabiti Majaribio sahihi Muda wa majibu (wastani) Tokeni za ingizo Tokeni za matokeo Tokeni za hoja
DeepSeek V3.2 2.9 7.2 11.1% 1 4.17s 624 21 0
Mercury 2 5.3 7.2 44.4% 1 534ms 784 46 0
Akili ya jumla Alama Uthabiti Kiwango cha kupita kwa kila jaribio Majaribio yasiyo thabiti Majaribio sahihi Muda wa majibu (wastani) Tokeni za ingizo Tokeni za matokeo Tokeni za hoja
DeepSeek V3.2 4.7 1.6 66.7% 1 9.32s 314 43 0
Mercury 2 4.8 10.0 0.0% 0 628ms 495 159 0
Ufuataji wa maagizo Alama Uthabiti Kiwango cha kupita kwa kila jaribio Majaribio yasiyo thabiti Majaribio sahihi Muda wa majibu (wastani) Tokeni za ingizo Tokeni za matokeo Tokeni za hoja
DeepSeek V3.2 10.0 10.0 100.0% 0 1.52s 627 66 0
Mercury 2 6.5 10.0 50.0% 0 551ms 691 82 0
Utatuzi wa mafumbo Alama Uthabiti Kiwango cha kupita kwa kila jaribio Majaribio yasiyo thabiti Majaribio sahihi Muda wa majibu (wastani) Tokeni za ingizo Tokeni za matokeo Tokeni za hoja
DeepSeek V3.2 7.6 7.2 77.8% 1 6.91s 424 298 0
Mercury 2 3.1 10.0 0.0% 0 535ms 694 251 0
Mwito wa zana Alama Uthabiti Kiwango cha kupita kwa kila jaribio Majaribio yasiyo thabiti Majaribio sahihi Muda wa majibu (wastani) Tokeni za ingizo Tokeni za matokeo Tokeni za hoja
DeepSeek V3.2 10.0 10.0 100.0% 0 11.85s 8,319 522 0
Mercury 2 10.0 10.0 100.0% 0 1.27s 6,193 197 0
Maarifa ya jumla Alama Uthabiti Kiwango cha kupita kwa kila jaribio Majaribio yasiyo thabiti Majaribio sahihi Muda wa majibu (wastani) Tokeni za ingizo Tokeni za matokeo Tokeni za hoja
DeepSeek V3.2 3.0 10.0 0.0% 0 17.23s 183 17 0
Mercury 2 3.0 10.0 0.0% 0 548ms 213 19 0

Ulinganisho wa haraka

Badilisha jozi ya ulinganisho

DeepSeek V3.2nonevsMistral Small 4mediumDeepSeek V3.2nonevsMiniMax M2.7mediumDeepSeek V3.2nonevsMiniMax M2.5mediumDeepSeek V3.2nonevsElephant AlphamediumMercury 2nonevsQwen3 Coder NextmediumMercury 2nonevsGLM 4.7 FlashmediumMercury 2nonevsQwen3.5-9BmediumCobuddymediumvsDeepSeek V3.2noneDeepSeek V3.2nonevsOwl AlphamediumDeepSeek V3.2nonevsgpt-oss-120bmediumInapatikana bureDeepSeek V3.2nonevsNemotron 3 SupermediumInapatikana bureDeepSeek V3.2nonevsQwen3 Coder Nextmedium